INDEX

Explanations

terms related to the concept of "negation" or "denial."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã³s

-0.17

 downs

-0.14

 Peninsula

-0.14

llu

-0.14

apps

-0.14

oji

-0.14

riger

-0.14

 Barbar

-0.13

ques

-0.13

usercontent

-0.13

POSITIVE LOGITS

neg

0.20

atively

0.20

Neg

0.19

Neg

0.18

lected

0.17

 Hamm

0.17

ativ

0.17

entropy

0.17

ativnÃŃ

0.16

 negoci

0.16

Activations Density 0.010%

terms related to the concept of "negation" or "denial."

No Comments

No Known Activations